ORION%20Project-team - PowerPoint PPT Presentation

About This Presentation
Title:

ORION%20Project-team

Description:

Annie Ressouche (CR1 Inria) (team leader) Monique Thonnat (DR1 Inria) ... Le Thi Lan, Mohamed Becha Kaaniche, Vincent Martin, Marcos Zuniga. Team presentation ... – PowerPoint PPT presentation

Number of Views:86
Avg rating:3.0/5.0
Slides: 28
Provided by: Moka
Category:
Tags: 20project | orion | team

less

Transcript and Presenter's Notes

Title: ORION%20Project-team


1
ORION Project-team
  • Monique THONNAT
  • INRIA Sophia Antipolis

Creation July 1995 Multidisciplinary team
artificial intelligence, software engineering,
computer vision
2
Contents
  • Team Presentation
  • Research Directions
  • Cognitive Vision 2002-2006
  • Reusable Systems 2002-2006
  • Objectives for the next Period

3
Team presentation (May 2006)
  • 4 Research Scientists François Bremond (CR1
    Inria)
  • Sabine Moisan (CR1 Inria, HDR)
  • Annie
    Ressouche (CR1 Inria)
  • (team leader) Monique Thonnat (DR1 Inria)
  • 1 External Collaborator Jean-Paul Rigault
    (Prof. UNSA Inria secondment)
  • 4 Temporary Engineers Etienne Corvee, Ruihua
    Ma, Valery Valentin,
    Thinh Van Vu
  • 7 PhD Students Bui Binh, Bernard
    Boulay, Naoufel Kayati,
  • Le Thi Lan,
    Mohamed Becha Kaaniche,
  • Vincent
    Martin, Marcos Zuniga

4
Research directions
  • Objective
  • Intelligent Reusable Systems for Cognitive
    Vision
  • Cognitive Vision
  • Interpretation of static images
  • Video understanding
  • Reusable Systems
  • Program Supervision
  • LAMA Software platform

5
Orion team positioning
  • Cognitive Vision
  • Image interpretation (ECVision European network
    on cognitive vision, EUCognition) vs. computer
    vision (INRIA CogB)
  • Video understanding (USC Los Angeles, Georgia
    Tech. Atlanta, Univ. Central Florida, NUCK
    Taiwan, Univ. Kingston UK, INRIA Prima)
  • Reusable Systems
  • Program supervision e.g., scheduling (ASPEN and
    CASPER at JPL), image processing (Hermès at
    Univ. Caen, ExTI at IRIT)
  • Platform approach e.g., ontology management
    (Protegé at Stanford), frameworks for multi
    agents (Aglets, Jade, Oasis at LIP6), distributed
    object community (Oasis at INRIA Sophia)

6
Cognitive Vision Image Interpretation
2002-2006
  • Objective semantic interpretation of static 2D
    images
  • Recognition of object categories (versus
    individuals)
  • Recognition of scenes involving several objects
    with spatial reasoning
  • Intelligent management of image processing
    programs
  • Towards a cognitive
    vision platform

7
Cognitive Vision Image Interpretation
2002-2006
  • Scientific achievements
  • Knowledge acquisition
  • A visual concept ontology with 144 spatial, color
    and texture concepts MVA04
  • Learning
  • Visual concept detectors IVC06
  • Image segmentation parameters ICVSa06
  • Cognitive vision platform
  • Architecture ICVS03
  • Object class recognition algorithm CIVR05

8
Cognitive Vision Image Interpretation
2002-2006
  • Self Assessment
  • Strong points
  • Visual concept ontology as user-friendly
    intermediate layer between image processing and
    application domain
  • Automatic building of the visual concept
    detectors
  • Still open issues
  • Learning for image segmentation
  • Temporal visual concept ontology

9
Cognitive Vision Video Understanding 2002-2006
  • Objective
  • Real time recognition of interesting behaviors
  • How?
  • Data captured by video surveillance cameras
  • Original video understanding approach mixing
  • computer vision 4D analysis (3D temporal
    analysis)
  • artificial intelligence a priori knowledge
    (scenario, environment)
  • software engineering reusable VSIP platform

10
Cognitive Vision Video Understanding
2002-2006
Objective Interpretation of videos from pixels
to alarms
Segmentation
Classification
Scenario Recognition
Tracking
Alarms
access to forbidden area
3D scene model Scenario models
A priori Knowledge
11
Cognitive Vision Video Understanding
2002-2006
  • Scientific achievements
  • Multi-sensor video understanding
  • 2 to 4 video cameras overlapping or not
    IDSS03,JASP05
  • Video cameras optical cells contact sensors
    AVSS05
  • Learning
  • parameter tuningMVAa06
  • frequent temporal scenarios models ICVSb06
  • Temporal scenario
  • a new real time recognition algorithm
    IJCAI03,ICVS03
  • a new representation language MVAb06,ECAI02,KES02

12
Cognitive Vision Video Understanding
2002-2006
  • Industrial impact
  • Strong impact in visual surveillance (metro
    station, bank agency, building access control,
    onboard train, airport)
  • 4 European projects (ADVISOR, AVITRACK, SERKET,
    CARETAKER)
  • 5 industrial contracts with RATP, ALSTOM, SNCF,
    Credit Agricole, STMicroelectronics
  • 2 transfer activities with BULL (Paris), VIGITEC
    (Brussels)
  • Creation of a start-up Keeneo July 2005 (8
    persons) for industrialization and exploitation
    of VSIP library.

13
Cognitive Vision Video Understanding
2002-2006
Intelligent video surveillance of Bank agencies
14
Cognitive Vision Video Understanding 2002-2006
  • Unloading Global Operation

15
Cognitive Vision Video Understanding
2002-2006
  • Airport Apron Monitoring Unloading Operation
  • European AVITRACK project

16
Cognitive VisionVideo Understanding 2002-2006
  • Self Assessment
  • Strong points
  • Video understanding approach real time,
    effective techniques used by external academic
    and industrial teams
  • Launch of an evaluation competition for video
    surveillance algorithms (ETISEO) with currently
    25 international teams
  • Still open issues
  • Learning
  • Multi sensor

17
Reusable Systems Program Supervision
  • Reusable Systems original approach for the
    reuse of programs with program supervision
    techniques
  • Program supervision
  • Automate the (re)configuration and execution of
    programs
  • selection, scheduling, execution, and control of
    results
  • Knowledge-based approach knowledge modeling,
    planning techniques, ..

18
Reusable Systems LAMA Platform
  • Reusable Systems
  • Reuse of tools to design knowledge-based systems
    (KBS)
  • LAMA Software Platform
  • Set of toolkits to facilitate design and
    evolution of KBS elements
  • engines, GUI, knowledge languages, learning and
    verification facilities
  • Software Engineering approach genericity,
    frameworks, objects and components

LAMA
raise new issues, to be abstracted into new
components
provide generic components and tools
Problem Solving KBS
Virtuous Circle
19
Reusable Systems LAMA Platform
20
Reusable Systems Program Supervision 2002-2006
  • Scientific achievements
  • Improvement of the Pegase engine (Pegase)
  • Multithreading, extensions to the YAKL language
    ECAI02
  • Distributed program supervision
  • Supervision Web server, multi-agent techniques,
    interoperability Pegase/Java/agents TC06
  • Cooperation with image and video understanding
  • Object recognition task using program supervision
    ICTAI03
  • Interoperability with VSIP program supervision
    for video understanding ICVSc06

21
Reusable Systems LAMA Platform 2002-2006
  • Scientific achievements
  • Enforcing LAMA safe usage
  • Verification of LAMA component extensions relying
    on Model Checking approach Informatica01,
    SEFM04
  • Encompassing new tasks
  • Classification and object recognition in images
    new engine and new knowledge representation
    language ICTAI03
  • Model calibration in hydraulics new
    engine/language (PhD co-directed with INPT and
    CEMAGREF) KES03, JH05

22
Reusable Systems Self Assessment
  • Strong points
  • Real time performance (Pegase and video)
  • Using program supervision costs less than 5 of
    overall processing time
  • LAMA genericity at work
  • Different tasks (supervision, classification,
    calibration) in various application domains
    (hydraulics, biology, astronomy, video
    surveillance)
  • Shorter development time and safer code
  • Reuse of concepts as well as code
  • Several variants of a task sharing common
    concepts
  • Extensibility and commitment to Standards

23
Objectives for the next period 1/5
  • Creation of a new INRIA project-team PULSAR
  • Perception Understanding and Learning Systems
    for Activity Recognition
  • Theme
  • CogC Multimedia data interpretation and
    man-machine interaction
  • Multidisciplinary team
  • artificial intelligence, software engineering,
    computer vision
  • Objective
  • Research on Cognitive Systems for Activity
    Recognition
  • Focus on spatiotemporal activities of physical
    objects
  • From sensor output to high level interpretation

24
Objectives for the next period 2/5
  • PULSAR Scientific objectives
  • Two research axes
  • Scene Understanding for Activity Recognition
  • Generic Components for Activity Recognition
  • PULSAR Applications
  • Safety/security (e.g. intelligent surveillance)
  • Healthcare (e.g. assistance to the elderly)

25
Objectives for the next period 3/5
  • PULSAR Scene Understanding for Activity
    Recognition
  • Perception multi-sensors, finer descriptors
  • Understanding uncertainty, 4D coherency,
    ontology for AR
  • Learning parameter setting, event detector,
    activity models, program supervision KB (risky
    objective)

26
Objectives for the next period 4/5
  • PULSAR Generic Components for Activity
    Recognition
  • From LAMA Platform to AR platform
  • Model extensions
  • modeling time and scenarios
  • handling uncertainty
  • User-friendliness and safeness of use
  • theory and tools for component frameworks
  • scalability of verification methods
  • Architecture improvement
  • parallelization, distribution, concurrence
  • real time response
  • domain specific software and graphical interface
    plugging

27
Objectives for the next period 5/5
  • Short term objectives
  • Scene Understanding for Activity Recognition
  • Perception gesture analysis
  • Understanding
  • ontology-based activity recognition
  • uncertainty management
  • Learning primitive event detectors learning
  • Generic Components for Activity Recognition
  • Model of time and scenarios
  • Internal concurrency and distributed architecture
Write a Comment
User Comments (0)
About PowerShow.com